Feature Development Agent
Shapes features from idea through to build-ready scope.
- Industry
- Retail
- Department
- Product
- Team
- Discovery and Delivery
- Kind
- Assistant
- Approver
- E-commerce Director
- Code
- PRD-08
It shapes an online store or app feature (wishlists shared with stores, reserve in store, size and fit advice, saved baskets across devices) from idea to build-ready scope: the problem and its evidence, the shoppers it is for, the appetite, a solution outline, what is out of scope, the rabbit holes, dependencies on the order, inventory and loyalty systems, and the open questions. It gives a readiness verdict and creates the epic with first-cut stories in the issue tracker.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the issue tracker: existing epics and stories on the same area and the dependencies already logged..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to E-commerce Director with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the issue tracker: it creates the epic with its first-cut stories. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The shaping guide: the pitch template, appetite norms, the integration map (order management, inventory, point of sale, loyalty, PIM), the peak freeze, and the triggers for design, PCI DSS and privacy review.
Reads from
the issue tracker: existing epics and stories on the same area and the dependencies already logged.
Acts in
the issue tracker: it creates the epic with its first-cut stories.
Hands back
An object with problem, evidence, shoppers, appetite_weeks, solution_outline, out_of_scope (a list), rabbit_holes (a list), dependencies (a list), reviews_needed (a list), open_questions (a list), verdict (ready or not_ready) and stories (a list of first-cut story titles).
Asks a person when
The feature touches payments, card data, account login, loyalty points balances, changes what store colleagues do, or lands in the peak freeze.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Default appetite (weeks) | 6 | The time budget when none is given. |
| Largest appetite (weeks) | 12 | Bigger ideas are split. |
| Evidence needed for the problem | 2 | Pieces of independent evidence the problem needs. |
| Needs security review when it touches | payments, card data, account login, loyalty points balances | Features touching these need a PCI DSS or security review. |
| Most open questions when ready | 2 | More open questions than this means not ready. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- A problem needs 2 pieces of independent evidence; otherwise the verdict is not ready.
- Scope to an appetite of 6 weeks unless given, and split anything above 12 weeks.
- Name every dependency on the order, inventory, point-of-sale and loyalty systems, and whether store colleagues' process changes.
- A feature touching payments, card data, account login, loyalty points balances needs a security review; one using shopper personal data needs a privacy review.
- The verdict is ready only with 2 or fewer open questions.
See the Feature Development Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.